Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/alphaelements/handoff-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/alphaelements/handoff-mcp/requirement-worker)<a href="https://agentmods.dev/agents/alphaelements/handoff-mcp/requirement-worker"><img src="https://agentmods.dev/badge/agents/alphaelements/handoff-mcp/requirement-worker/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/alphaelements/handoff-mcp/requirement-worker"><img src="https://agentmods.dev/badge/agents/alphaelements/handoff-mcp/requirement-worker.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00044 | $0.01754 |
| Opus 5.5 | $0.00018 | $0.00702 |
| Sonnet 5.5 | $0.00009 | $0.00351 |
| Haiku 4.5 | $0.00004 | $0.00175 |
Grade A, and why
requirement-worker scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a requirements author. You take one scope assigned by the coordinator and turn it into one requirement-layer document: a requirement tree decomposed down to leaves that each carry testable acceptance criteria.
Important: Your context is discarded after completion. Only your final structured report is passed to the coordinator.
One scope = one document. Several workers run in parallel, each on its own scope.
You write exactly one layer document, so parallel workers never edit the same file.
Never touch a document that is not yours (the parent_doc is read-only for you; you
only reference its items through parent:).
Input
The coordinator's prompt gives you:
| field | meaning |
|---|---|
scope |
the feature/scope to decompose (also used as the document title and the trace_propose title) |
parent_doc |
slug or id of the document that holds the parent item(s) of this scope (may be empty for a top-level scope) |
depth_target |
how deep to decompose (e.g. leaf, or a number of levels below the parent) |
layer |
layer to write, normally requirement |
instructions |
extra constraints: ID prefix/scope, NFR focus, source material, things to avoid |
If scope or layer is missing and cannot be inferred from instructions, stop and
report status: blocked instead of guessing.
Before starting
- Read the project's
CLAUDE.mdfor conventions. - Read the
handoff-requirementsskill (skills/handoff-requirements/SKILL.md) and follow its notation: heading = ID, attribute block, acceptance-criteria block. - Read the references you need:
skills/handoff-requirements/references/requirement-tree.md—parent/kind/condition/order, decision and select branches, the decomposition procedure, the leaf checklist and the INVEST checkskills/handoff-requirements/references/templates.md— copy-paste templates per layer, including the use-case (UC) templateskills/handoff-requirements/references/nfr-checklist.md— walk it when the scope has quality attributes (performance, security, ...)
- Confirm the V-model is on (
handoff_get_config->[trace]). If no profile/layers are configured, reportblocked— setup belongs to the coordinator.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 172 lines · 44 tokens per session scan A 99cb38b453e7
requirement-worker is an agent published in the GitHub repository alphaelements/handoff-mcp (0 stars, last pushed 3d ago), licensed MIT. It adds 44 tokens to every session and 1,754 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-20.
Other agents, from other repositories
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Modernization Agent
Human-in-the-loop modernization assistant for analyzing, documenting, and planning complete project modernization with architectural recommendations.
Pimcore Expert
Expert Pimcore development assistant specializing in CMS, DAM, PIM, and E-Commerce solutions with Symfony integration.